Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, and the description restates the same properties (read-only, no network, no state, deterministic) - useful confirmation but not additive. It does add genuinely new operational context the annotations lack: JSON input capped at 64 KB, 1 s per call, and results up to 1 MB.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and well-structured into When/Not for/Side effects/Deterministic/Limits, but the entire block is duplicated in Spanish and English, roughly doubling length. Each individual language block is tight, yet the repetition is avoidable weight for an agent reading the definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and the description covers scope, limits, determinism and the routing alternative. For a deterministic pure-function crypto tool that is close to complete; only the interaction between input_encoding and key_encoding could be clearer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with three enums, so the baseline is 3; the description goes slightly beyond by framing data and key as independently encodable ('text, hex or base64 data with a text, hex or base64 key'), which signals the two encoding parameters interact. It still says nothing about output_encoding defaults in prose, which the schema covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Computes the HMAC (RFC 2104) using SHA384 over text, hex or base64 data with a text, hex or base64 key'), which unambiguously separates it from hash-sha384, hmac-sha256, hmac-sha512 and hmac-verify. The algorithm and encoding combinations are named, not implied.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'When: a message has to be signed, or a signature checked, with a shared secret supplied in the call' and 'Not for: checking an HMAC signature in constant time (hmac-verify)'. It names the alternative sibling and the condition that selects it, leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.